nttx commited on
Commit
0c011d1
·
verified ·
1 Parent(s): 2f26374

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c553098d5b7958cc9c70ff06a65fac512cfbba20a2542df0137f95b4be716c5c
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbea8a2fa5072b5a7d723904ee83b99aaf1b0df24818bbce2906e158dda936e6
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9ef018b497f82a54fdc885d73adedf45ef136b627e1b718434030acc94552da
3
  size 278249554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7cfe91b4d4f810d0002931f5c1f72e6e67998fedd96e206cb01574b9cd9c2f
3
  size 278249554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6d9e816852c96075831d528f89ebc882513936aa1d1448f620109d00fa158df
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a48f48f35db283ef3f13194b461f797bfb7469a36344847e7ba1a64f4c7209
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.229457378387451,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01681944327642755,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 37.418,
374
  "eval_steps_per_second": 18.713,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3451611968962560.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.184495449066162,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0336388865528551,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 37.418,
374
  "eval_steps_per_second": 18.713,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.017155832141956102,
379
+ "grad_norm": 0.2517932653427124,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 2.5462,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01749222100748465,
386
+ "grad_norm": 0.2670835554599762,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 2.5628,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.017828609873013202,
393
+ "grad_norm": 0.25449806451797485,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 2.3425,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.018164998738541754,
400
+ "grad_norm": 0.2293660193681717,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 2.525,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.018501387604070305,
407
+ "grad_norm": 0.20520225167274475,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 2.3914,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.018837776469598857,
414
+ "grad_norm": 0.1786617934703827,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 2.4665,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01917416533512741,
421
+ "grad_norm": 0.160075381398201,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 2.2621,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01951055420065596,
428
+ "grad_norm": 0.1475311666727066,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 2.2723,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.019846943066184508,
435
+ "grad_norm": 0.1324007511138916,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 2.4622,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02018333193171306,
442
+ "grad_norm": 0.12696845829486847,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 2.3154,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.02051972079724161,
449
+ "grad_norm": 0.12675370275974274,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 2.179,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020856109662770163,
456
+ "grad_norm": 0.11854014545679092,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 2.4794,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.021192498528298714,
463
+ "grad_norm": 0.134128600358963,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 2.0619,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.021528887393827266,
470
+ "grad_norm": 0.1273840367794037,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 2.1111,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.021865276259355814,
477
+ "grad_norm": 0.11819684505462646,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 2.3178,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.022201665124884366,
484
+ "grad_norm": 0.12865498661994934,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 2.3396,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.022538053990412917,
491
+ "grad_norm": 0.13002778589725494,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 2.1979,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02287444285594147,
498
+ "grad_norm": 0.12023420631885529,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 2.2783,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02321083172147002,
505
+ "grad_norm": 0.1349371373653412,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 2.257,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.023547220586998572,
512
+ "grad_norm": 0.13931462168693542,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 2.058,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02388360945252712,
519
+ "grad_norm": 0.12889568507671356,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 2.1331,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02421999831805567,
526
+ "grad_norm": 0.13493181765079498,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 2.1518,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.024556387183584223,
533
+ "grad_norm": 0.12535114586353302,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 2.3403,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.024892776049112775,
540
+ "grad_norm": 0.14284498989582062,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 2.2651,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.025229164914641326,
547
+ "grad_norm": 0.1374937891960144,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 2.2428,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.025565553780169878,
554
+ "grad_norm": 0.14151272177696228,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 2.1402,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.025901942645698426,
561
+ "grad_norm": 0.14077945053577423,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 2.2438,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.026238331511226978,
568
+ "grad_norm": 0.14996446669101715,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 2.0749,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02657472037675553,
575
+ "grad_norm": 0.14320829510688782,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 2.1752,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02691110924228408,
582
+ "grad_norm": 0.1642449051141739,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 2.2197,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.027247498107812632,
589
+ "grad_norm": 0.14916405081748962,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 2.0808,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.027583886973341184,
596
+ "grad_norm": 0.14916309714317322,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 2.1206,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.027920275838869732,
603
+ "grad_norm": 0.15080957114696503,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 2.2949,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.028256664704398284,
610
+ "grad_norm": 0.14866329729557037,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 1.9822,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.028593053569926835,
617
+ "grad_norm": 0.15501651167869568,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 2.2537,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.028929442435455387,
624
+ "grad_norm": 0.15602312982082367,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 2.0236,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.029265831300983938,
631
+ "grad_norm": 0.14871007204055786,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 2.1303,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02960222016651249,
638
+ "grad_norm": 0.16841718554496765,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 2.2095,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.029938609032041038,
645
+ "grad_norm": 0.18683014810085297,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 2.1266,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03027499789756959,
652
+ "grad_norm": 0.16032518446445465,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 2.2099,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03061138676309814,
659
+ "grad_norm": 0.1630275994539261,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 2.0045,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.030947775628626693,
666
+ "grad_norm": 0.18670861423015594,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 1.941,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03128416449415524,
673
+ "grad_norm": 0.17295370995998383,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 2.0762,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03162055335968379,
680
+ "grad_norm": 0.17951808869838715,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 2.0782,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.031956942225212344,
687
+ "grad_norm": 0.19968754053115845,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 2.0776,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.032293331090740895,
694
+ "grad_norm": 0.20060695707798004,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 2.0879,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03262971995626945,
701
+ "grad_norm": 0.22675327956676483,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 2.1727,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.032966108821798,
708
+ "grad_norm": 0.2281123250722885,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 2.1492,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03330249768732655,
715
+ "grad_norm": 0.27324235439300537,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 2.0096,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0336388865528551,
722
+ "grad_norm": 0.3571203052997589,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 2.0528,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0336388865528551,
729
+ "eval_loss": 2.184495449066162,
730
+ "eval_runtime": 134.0079,
731
+ "eval_samples_per_second": 37.363,
732
+ "eval_steps_per_second": 18.685,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6886051739074560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null